© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 31869
    Prev
    Next
    INDEX
    Explanations

    section headers like abstract introduction acknowledgment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ç§ģ
    -0.06
    åĽłæĤ¨çļĦ
    -0.06
     Kob
    -0.06
    andr
    -0.06
    è·Łè´´
    -0.06
     "
    -0.06
    panel
    -0.06
    åķĨæĬ¥
    -0.06
    ta
    -0.06
    ón
    -0.06
    POSITIVE LOGITS
    opedia
    0.08
    imientos
    0.08
    ovati
    0.07
    æ¡¥åĮº
    0.07
    slash
    0.07
    ProcessEvent
    0.07
    çŃĶçĸij解æĥij
    0.07
    arine
    0.07
    ewire
    0.07
    ður
    0.07
    Activations Density 0.013%

    No Known Activations